Improved image classification explainability with high-accuracy heatmaps

Preechakul, Konpat; Sriswasdi, Sira; Kijsirikul, Boonserm; Chuangsuwanich, Ekapol

doi:10.1016/j.isci.2022.103933

Cited by 15 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noted that PYLON [19] can produce both classification results and heatmaps. Moreover, PYLON does not require expert annotation of label position and can be trained with solely image-level labels.…”

Section: Proposed Methods a Our Modelmentioning

confidence: 99%

“…In 2022, Preechakul et al [19] demonstrated a pyramid localization network (PYLON), which generates higher resolution than the CAM method. PYLON does not need to map outputs and sum up weights like a traditional CAM.…”

Section: Class Activation Mapmentioning

confidence: 99%

“…The aim of our work is to present a real-time malignancy classification model, which is able to locate suspicious regions. PYLON [19] was selected and first applied to solve this problem. PYLON's model has been further improved in two aspects.…”

Section: Introductionmentioning

confidence: 99%

“…The experiments were carried out to compare our model with other methods e.g. ResNet50v2 [20], Xception [11], EfficientNet [12], and PYLON [19]. Results demonstrated that our model outperformed all baselines in terms of classification performance.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-Time Identification of Malignant Biliary Strictures on Cholangioscopy Images Using Explainable Convolutional Neural Networks With Heatmaps

Phuangthongkham,

Angsuwatcharakon,

Kulpatcharapong

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Determination of benign or malignant etiology of bile duct strictures is difficult. Currently, a digital single-operator cholangioscopy allows endoscopists to examine the bile duct with greater accuracy. Consequently, lesions in the bile duct can be detected directly with their own eyes. However, there is still inconsistency of diagnosis among endoscopists. Therefore, a biopsy is usually considered as a gold standard. Thus, pieces of tissue are taken from the bile duct and undergo examination. A false negative of cancer diagnosis from a sampling error of biopsy leads to the need to repeat procedures. In this work, we propose a convolutional neural network specifically designed for classifying malignant biliary strictures in real-time. In our development, this model can generate output not only for classification but also for a class activation map, which relies solely on an image-level label rather than annotation position. The model mainly focuses on tissues, not on equipment e.g. guide wire. To increase the number of cholangioscopy images, and solve the issue of equipment, ''a guide-wire augmentation'' is invented. To employ a video inference, our model for still images is further modified. In our experiment, all models are run on 3 patient-based bootstraps. The data contains 104 patients' records collected at King Chulalongkorn Memorial Hospital with 885 images: 447 malignant and 438 benign images. The model's performance for still images is 0.8577 and 0.8395 in terms of sensitivity and F1, respectively. With our video inference algorithm, the sensitivity of the model attains 0.9024 and the F1-score achieves 0.9193. Finally, the model can facilitate real-time inference with a speed of 83 frames per second. INDEX TERMS Deep learning, indeterminate biliary strictures, real-time image classification, explainable deep learning.The associate editor coordinating the review of this manuscript and approving it for publication was Carmelo Militello .

show abstract

Section: Proposed Methods a Our Modelmentioning

confidence: 99%

Section: Class Activation Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Identification of Malignant Biliary Strictures on Cholangioscopy Images Using Explainable Convolutional Neural Networks With Heatmaps

Phuangthongkham,

Angsuwatcharakon,

Kulpatcharapong

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Among various research topics on explainability in NLP, perhaps the most trending one is whether the attention can be treated as explanations . Unlike the attention in computer vision area, such as using attention heatmap to visualize how machine understands chest radiograph ( Preechakul et al., 2022 ), the explainability of the attention mechanism is still uncertain in NLP. Some researchers argue that attention could not be used as explanation.…”

Section: Introductionmentioning

confidence: 99%