Spaces:
Configuration error
Configuration error
File size: 17,151 Bytes
a01ef8c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 |
{
"cells": [
{
"cell_type": "markdown",
"id": "2e3e807d",
"metadata": {},
"source": [
"# Multimodal Cancer Detection using the Intel® Transfer Learning Tool API\n",
"\n",
"This application is a multimodal solution for predicting cancer diagnosis using categorized contrast enhanced mammography data and radiology notes. It trains two models - one for image classification and the other for text classification - which can be combined into an ensemble classifier.\n",
"\n",
"## Import Dependencies and Setup Directories"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f2a722a7",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import os\n",
"import pandas as pd\n",
"import tensorflow as tf\n",
"import torch\n",
"\n",
"from transformers import EvalPrediction, TrainingArguments\n",
"\n",
"# tlt imports\n",
"from tlt.datasets import dataset_factory\n",
"from tlt.models import model_factory\n",
"\n",
"# Specify the root directory where the images and annotations are located\n",
"dataset_dir = os.path.join(os.environ[\"DATASET_DIR\"]) if \"DATASET_DIR\" in os.environ else \\\n",
" os.path.join(os.environ[\"HOME\"], \"dataset\")\n",
"\n",
"# Specify a directory for output\n",
"output_dir = os.environ[\"OUTPUT_DIR\"] if \"OUTPUT_DIR\" in os.environ else \\\n",
" os.path.join(os.environ[\"HOME\"], \"output\")\n",
"\n",
"print(\"Dataset directory:\", dataset_dir)\n",
"print(\"Output directory:\", output_dir)"
]
},
{
"cell_type": "markdown",
"id": "bb53162b",
"metadata": {},
"source": [
"## Dataset\n",
"\n",
"Download the images and radiology annotations from https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=109379611\n",
"\n",
"Image files should have the .jpg extension and be arranged in subfolders for each class. The annotation file should be a .csv. The data directory should look something like this:\n",
"\n",
"```\n",
"brca\n",
" ├── annotation\n",
" │ └── annotation.csv\n",
" └── vision_images\n",
" ├── Benign\n",
" │ ├── P100_L_CM_CC.jpg\n",
" │ ├── P100_L_CM_MLO.jpg\n",
" │ └── ...\n",
" ├── Malignant\n",
" │ ├── P102_R_CM_CC.jpg\n",
" │ ├── P102_R_CM_MLO.jpg\n",
" │ └── ...\n",
" └── Normal\n",
" ├── P100_R_CM_CC.jpg\n",
" ├── P100_R_CM_MLO.jpg\n",
" └── ...\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bd9c3ef2",
"metadata": {},
"outputs": [],
"source": [
"# User input needed - supply the path to the images in the dataset_dir according to your system\n",
"source_image_path = os.path.join(dataset_dir, 'brca', 'vision_images')\n",
"image_path = source_image_path\n",
"\n",
"# User input needed - supply the path and name of the annotation file in the dataset_dir\n",
"source_annotation_path = os.path.join(dataset_dir, 'brca', 'annotation', 'annotation.csv')\n",
"annotation_path = source_annotation_path\n",
"label_col = 3 # Index of the label column in the data file"
]
},
{
"cell_type": "markdown",
"id": "245df47c",
"metadata": {},
"source": [
"### Optional: Group Data by Patient ID\n",
"\n",
"This section is not required to run the workload, but it is helpful to assign all of a subject's records to be entirely in the train set or test set. This section will do a random stratification based on patient ID and save new copies of the grouped data files."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "44dbd990",
"metadata": {},
"outputs": [],
"source": [
"from data_utils import split_images, split_annotation\n",
"\n",
"grouped_image_path = '{}_grouped'.format(source_image_path)\n",
"\n",
"if os.path.isdir(grouped_image_path):\n",
" print(\"Grouped directory already exists and will be used: {}\".format(grouped_image_path))\n",
"else:\n",
" split_images(source_image_path, grouped_image_path)\n",
"\n",
"image_path = grouped_image_path"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d21bdff",
"metadata": {},
"outputs": [],
"source": [
"file_dir, file_name = os.path.split(source_annotation_path)\n",
"grouped_annotation_path = os.path.join(file_dir, '{}_grouped.csv'.format(os.path.splitext(file_name)[0]))\n",
"\n",
"if os.path.isfile(grouped_annotation_path):\n",
" print(\"Grouped annotation already exists and will be used: {}\".format(grouped_annotation_path))\n",
"else:\n",
" train_dataset = split_annotation(file_dir, file_name, image_path)\n",
" train_dataset.to_csv(grouped_annotation_path)\n",
" print('Grouped annotation saved to: {}'.format(grouped_annotation_path))\n",
"\n",
"annotation_path = grouped_annotation_path\n",
"label_col = 1 # Index of the label column in the grouped data file"
]
},
{
"cell_type": "markdown",
"id": "01e9e5cf",
"metadata": {},
"source": [
"## Model 1: Image Classification with TensorFlow\n",
"\n",
"### Get the Model and Dataset\n",
"Call the model factory to get a pretrained model from TensorFlow Hub and the dataset factory to load the images from their location. The `get_model` function returns a model object that will later be used for training. We will use resnet_v1_50 by default."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d9c93b18",
"metadata": {},
"outputs": [],
"source": [
"model = model_factory.get_model(model_name=\"resnet_v1_50\", framework='tensorflow')\n",
"\n",
"# Load the dataset from the custom dataset path\n",
"dataset = dataset_factory.load_dataset(dataset_dir=image_path,\n",
" use_case='image_classification',\n",
" framework='tensorflow')\n",
"\n",
"print(\"Class names:\", str(dataset.class_names))"
]
},
{
"cell_type": "markdown",
"id": "6472bedd",
"metadata": {},
"source": [
"### Data Preparation\n",
"Once you have your dataset loaded, use the following cell to preprocess the dataset. We split the images into training and validation subsets, resize them to match the model, and then batch the images."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "98dcf057",
"metadata": {},
"outputs": [],
"source": [
"batch_size = 16\n",
"if 'grouped' not in image_path:\n",
" # Split if not pre-defined\n",
" dataset.shuffle_split(train_pct=.80, val_pct=0.0, test_pct=0.2)\n",
"dataset.preprocess(model.image_size, batch_size=batch_size)"
]
},
{
"cell_type": "markdown",
"id": "f2f49c77",
"metadata": {},
"source": [
"### Transfer Learning\n",
"\n",
"This step calls the model's train function with the dataset that was just prepared. The training function will get the TFHub feature vector and add on a dense layer based on the number of classes in the dataset. The model is then compiled and trained based on the number of epochs specified in the argument. We also add two more dense layers using the `extra_layers` parameter.\n",
"\n",
"To optionally insert additional dense layers between the base model and output layer, `extra_layers=[1024, 512]` will insert two dense layers, the first with 1024 neurons and the second with 512 neurons."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "21a92e4e",
"metadata": {},
"outputs": [],
"source": [
"history = model.train(dataset, output_dir=output_dir, epochs=5, seed=10, extra_layers=[1024, 512], do_eval=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "45289d48",
"metadata": {},
"outputs": [],
"source": [
"metrics = model.evaluate(dataset, use_test_set=True)\n",
"for metric_name, metric_value in zip(model._model.metrics_names, metrics):\n",
" print(\"{}: {}\".format(metric_name, metric_value))"
]
},
{
"cell_type": "markdown",
"id": "bce6bafe",
"metadata": {},
"source": [
"### Save the Computer Vision Model"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "093905b2",
"metadata": {},
"outputs": [],
"source": [
"saved_model_dir = model.export(output_dir)"
]
},
{
"cell_type": "markdown",
"id": "5621b571",
"metadata": {},
"source": [
"## Model 2: Text Classification with PyTorch\n",
"\n",
"### Get the Model and Dataset\n",
"Now we will call the model factory to get a pretrained model from Hugging Face and load the annotation file using the dataset factory. We will use clinical-bert for this part."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d18cebff",
"metadata": {},
"outputs": [],
"source": [
"# Set up NLP parameters\n",
"model_name = 'clinical-bert'\n",
"seq_length = 64\n",
"batch_size = 5\n",
"quantization_criterion = 0.05\n",
"quantization_max_trial = 50\n",
"epochs = 3"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d939924f",
"metadata": {},
"outputs": [],
"source": [
"model = model_factory.get_model(model_name=model_name, framework='pytorch')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2e9dff00",
"metadata": {},
"outputs": [],
"source": [
"# Create a label map function and reverse label map for the dataset\n",
"def label_map_func(label):\n",
" if label == 'Benign':\n",
" return 0\n",
" elif label == 'Malignant':\n",
" return 1\n",
" elif label == 'Normal':\n",
" return 2\n",
" \n",
"reverse_label_map = {0: 'Benign', 1: 'Malignant', 2: 'Normal'}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "879bad74",
"metadata": {},
"outputs": [],
"source": [
"file_dir, file_name = os.path.split(annotation_path)\n",
"dataset = dataset_factory.load_dataset(dataset_dir=file_dir,\n",
" use_case='text_classification',\n",
" framework='pytorch',\n",
" dataset_name='brca',\n",
" csv_file_name=file_name,\n",
" label_map_func=label_map_func,\n",
" class_names=['Benign', 'Malignant', 'Normal'],\n",
" header=True,\n",
" label_col=label_col,\n",
" shuffle_files=True)"
]
},
{
"cell_type": "markdown",
"id": "e2b9ddba",
"metadata": {},
"source": [
"### Data Preparation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b166b757",
"metadata": {},
"outputs": [],
"source": [
"dataset.preprocess(model.hub_name, batch_size=batch_size, max_length=seq_length)\n",
"dataset.shuffle_split(train_pct=0.67, val_pct=0.33)"
]
},
{
"cell_type": "markdown",
"id": "020303ee",
"metadata": {},
"source": [
"### Transfer Learning\n",
"\n",
"This step calls the model's train function with the dataset that was just prepared. The training function will get the pretrained model from HuggingFace and add on a dense layer based on the number of classes in the dataset. The model is then trained using an instance of Hugging Face Trainer for the number of epochs specified. If desired, a native PyTorch loop can be invoked instead of Trainer by setting `use_trainer=False`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "41fb0612",
"metadata": {},
"outputs": [],
"source": [
"history = model.train(dataset, output_dir, epochs=epochs, use_trainer=True)"
]
},
{
"cell_type": "markdown",
"id": "de70a029",
"metadata": {},
"source": [
"### Save the NLP Model"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ba08847d",
"metadata": {},
"outputs": [],
"source": [
"model.export(output_dir)"
]
},
{
"cell_type": "markdown",
"id": "45752dd6",
"metadata": {},
"source": [
"### Int8 Quantization\n",
"\n",
"We can use the [Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers) to quantize the trained model for faster inference. If you want to run this part of the notebook, make sure you have `intel-extension-for-transformers` installed in your environment."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "44036b44",
"metadata": {},
"outputs": [],
"source": [
"!pip install intel-extension-for-transformers==1.0.1"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ce0687ce",
"metadata": {},
"outputs": [],
"source": [
"from intel_extension_for_transformers.optimization.trainer import NLPTrainer\n",
"from intel_extension_for_transformers.optimization import metrics, objectives, OptimizedModel, QuantizationConfig"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f9557a68",
"metadata": {},
"outputs": [],
"source": [
"# Set up quantization config\n",
"tune_metric = metrics.Metric(\n",
" name=\"eval_accuracy\",\n",
" greater_is_better=True,\n",
" is_relative=True,\n",
" criterion=quantization_criterion,\n",
" weight_ratio=None,\n",
")\n",
"\n",
"objective = objectives.Objective(\n",
" name=\"performance\", greater_is_better=True, weight_ratio=None\n",
")\n",
"\n",
"quantization_config = QuantizationConfig(\n",
" approach=\"PostTrainingDynamic\",\n",
" max_trials=quantization_max_trial,\n",
" metrics=[tune_metric],\n",
" objectives=[objective],\n",
")\n",
"\n",
"# Set up metrics computation\n",
"def compute_metrics(p: EvalPrediction):\n",
" preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions\n",
" preds = np.argmax(preds, axis=1)\n",
" return {\"accuracy\": (preds == p.label_ids).astype(np.float32).mean().item()}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f406d6db",
"metadata": {},
"outputs": [],
"source": [
"quantizer = NLPTrainer(model=model._model,\n",
" train_dataset=dataset.train_subset,\n",
" eval_dataset=dataset.validation_subset,\n",
" compute_metrics=compute_metrics,\n",
" tokenizer=dataset._tokenizer)\n",
"quantized_model = quantizer.quantize(quant_config=quantization_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "56e5f2f5",
"metadata": {},
"outputs": [],
"source": [
"results = quantizer.evaluate()\n",
"eval_acc = results.get(\"eval_accuracy\")\n",
"print(\"Final Eval Accuracy: {:.5f}\".format(eval_acc))"
]
},
{
"cell_type": "markdown",
"id": "b69df1a0",
"metadata": {},
"source": [
"## Citations\n",
"\n",
"### Data Citation\n",
"Khaled R., Helal M., Alfarghaly O., Mokhtar O., Elkorany A., El Kassas H., Fahmy A. <b>Categorized Digital Database for Low energy and Subtracted Contrast Enhanced Spectral Mammography images [Dataset].</b> (2021) The Cancer Imaging Archive. DOI: [10.7937/29kw-ae92](https://doi.org/10.7937/29kw-ae92)\n",
"\n",
"### Publication Citation\n",
"Khaled, R., Helal, M., Alfarghaly, O., Mokhtar, O., Elkorany, A., El Kassas, H., & Fahmy, A. <b>Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research.</b> (2022) Scientific Data, Volume 9, Issue 1. DOI: [10.1038/s41597-022-01238-0](https://doi.org/10.1038/s41597-022-01238-0)\n",
"\n",
"### TCIA Citation\n",
"Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. <b>The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository</b>, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. DOI: [10.1007/s10278-013-9622-7](https://doi.org/10.1007/s10278-013-9622-7)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|