Histopathological Image Classification: Defying Deep Architectures on Complex Data

Tripathi, Suvidha; Singh, Satish Kumar

doi:10.1007/978-981-13-9184-2_33

Cited by 3 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, directly feeding raw medical images as we do in the case of ImageNet dataset [19] to the deep model does not guarantee efficiency and performance. The same has been observed and proved through our experiments in [20] that state of the art deep learning models alone should not be relied upon for the tasks involving complex medical datasets.…”

Section: Introductionsupporting

confidence: 83%

“…BoVW as a feature selection method created the marked difference between the two methods. The results reflect the fact that deep learning alone, even after fine-tuning, cannot be regarded as an optimal method for the classification of complex data [20]. To train a deep learning model from scratch in our case was not an option due to lack of enough sample points for the model to be able to generalize well.…”

Section: Discussionmentioning

confidence: 65%

See 1 more Smart Citation

Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours

Tripathi¹,

Singh²,

Kuan³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Currently, the computational complexity limits the training of high resolution gigapixel images using Convolutional Neural Networks. Therefore, such images are divided into patches or tiles. Since, these high resolution patches are encoded with discriminative information therefore; CNNs are trained on these patches to perform patch-level predictions. It is a most sought-after approach for solving gigapixel classification and segmentation problems. Patch level predictions could also be used to detect new regions in the biopsy samples taken from the same patient at the same site. In other words, once the patient slide has been trained with the model, biopsy samples taken at a later stage to find whether the tumour has spread could be tested using the trained model. However, the problem with patch-level prediction is that pathologist generally annotates at image-level and not at patch level. Therefore, certain patches within the image, since not annotated finely by the experts, may not contain enough class-relevant features. Moreover, standard CNN generate a high dimensional feature set per image, if we train CNN just by patch level, it may pick up features specific to the training set and hence, not generalizable. Through this work, we tried to incorporate patch descriptive capability within the deep framework by using Bag of Visual Words (BoVW) as a kind of regularisation to improve generalizability. BoVW-a traditional handcrafted feature descriptor is known to show good descriptive capability along with feature interpretability. Using this hypothesis, we aim to build a patch based classifier to discriminate between four classes of breast biopsy image patches (normal, benign, In situ carcinoma, invasive carcinoma) in respect to better patch discriminative features embedded within the classification pipeline. The aim is to incorporate quality deep features using CNN to describe relevant information in the images while simultaneously discarding irrelevant information using Bag of Visual Words (BoVW). The proposed method passes patches obtained from WSI and microscopy images through pre-trained CNN to extract features. BoVW is used as a feature selector to select most discriminative features among the CNN features. Finally, the selected feature sets are classified as one of the four classes. The hybrid model provides flexibility in terms of choice of pre-trained models for feature extraction. Moreover, the pipeline is end-to-end since it does not require post processing of patch predictions to select discriminative patches. We compared our observations with state-of-the-art methods like ResNet50, DenseNet169, and Incep-

show abstract

Section: Introductionsupporting

confidence: 83%

Section: Discussionmentioning

confidence: 65%

Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours

Tripathi¹,

Singh²,

Kuan³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To justify our hypothesis, we have performed a detailed analysis of classification performance with HC-F descriptors and DL models. Why DL methods are insufficient for such problems can be understood through our study in [4]. The experimental analysis concluded in this study forms the base of our work.…”

Section: Arxiv:220210694v1 [Cscv] 22 Feb 2022mentioning

confidence: 80%

“…The experimental analysis concluded in this study forms the base of our work. In [4], we investigated relatively older deep architectures like AlexNet, VGG16, and VGG19 for their performance on classifying the nuclei dataset. While they gave state of the art performance with ImageNet dataset [5], these models could not perform at par with histopathological data.…”

Section: Arxiv:220210694v1 [Cscv] 22 Feb 2022mentioning

confidence: 99%

Ensembling handcrafted features with deep features: an analytical study for classification of routine colon cancer histopathological nuclei images

Tripathi

Singh

2020

Multimed Tools Appl

View full text Add to dashboard Cite

The use of Deep Learning (DL) based methods in medical histopathology images have been one of the most sought after solutions to classify, segment, and detect diseased biopsy samples. However, given the complex nature of medical datasets due to the presence of intra-class variability and heterogeneity, the use of complex DL models might not give the optimal performance up to the level which is suitable for assisting pathologists. Therefore, ensemble DL methods with the scope of including domain agnostic handcrafted Features (HC-F) inspired this work. We have, through experiments, tried to highlight that a single DL network (domain-specific or state of the art pre-trained models) cannot be directly used as the base model without proper analysis with the relevant dataset. We have used F1-measure, Precision, Recall, AUC, and Cross-Entropy Loss to analyse the performance of our approaches. We observed from the results that the DL features ensemble bring a marked improvement in the overall performance of the model, whereas, domain agnostic HC-F remains dormant on the performance of the DL models.

show abstract

Leveraging CNN and Transfer Learning for Classification of Histopathology Images

Dubey

Singh

Jiang

2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Histopathological Image Classification: Defying Deep Architectures on Complex Data

Cited by 3 publications

References 15 publications

Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours

Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours

Ensembling handcrafted features with deep features: an analytical study for classification of routine colon cancer histopathological nuclei images

Leveraging CNN and Transfer Learning for Classification of Histopathology Images

Contact Info

Product

Resources

About