Explainable survival analysis with uncertainty using convolution-involved vision transformer.

Image-based precision medicine research is able to help doctors make better decisions on treatments. Among all kinds of medical images, a special form is called Whole Slide Image (WSI), which is used for diagnosing patients with cancer, aiming to enable more accurate survival prediction with its high resolution. However, One unique challenge of the WSI-based prediction models is processing the gigabyte-size or even terabyte-size WSIs, which would make most models computationally infeasible. Although existing models mostly use a pre-selected subset of key patches or patch clusters as input, they might discard some important morphology information, making the prediction inferior. Another challenge is improving the prediction models' explainability, which is crucial to help doctors understand the predictions given by the models and make faithful decisions with high confidence. To address the above two challenges, in this work, we propose a novel explainable survival prediction model based on Vision Transformer. Specifically, we adopt dual-channel convolutional layers to utilize the complete WSIs for more accurate predictions. We also introduce the aleatoric uncertainty into our model to understand its limitation and avoid overconfidence in using the prediction results. Additionally, we present a post-hoc explainable method to identify the most salient patches and distinct morphology features as supporting evidence for predictions. Evaluations of two large cancer datasets show that our proposed model is able to make survival predictions more effectively and has better explainability for cancer diagnosis.

Transoral Endoscopic Thyroidectomy Vestibular Approach (TOETVA): Influences on the Voice Changes and Swallowing Function Disorders.

OBJECTIVE: The aim of this study was to evaluate the influence of transoral endoscopic thyroidectomy vestibular approach (TOETVA) on voice changes and swallowing function disorders. MATERIALS AND METHODS: We retrospectively reviewed 215 patients who underwent thyroid surgery with TOETVA (105 cases, endoscopic group) and open approach (110 cases, open group). Major outcomes, the changes in voice and swallowing function in the 2 groups of patients before and after surgery were analyzed by using both subjective and objective evaluation indexes. Subjective evaluation indexes included the Voice Handicap Index, voice GRBAS (Grade, Roughness, Breathiness, Asthenia, Strain) classification, and swallowing impairment score; the objective indicators included the fundamental frequency (F0), fundamental frequency perturbation (jitter), amplitude perturbation (shimmer), and maximum phonation time. RESULTS: In terms of subjective evaluation indexes, there were no significant differences (all P> 0.05) between the groups regarding Voice Handicap Index (1 and 3 mo after surgery) and GRBAS (1 and 3 mo after surgery). The incidence rates of swallowing disorder in the endoscopic group were higher than that in the open group according to the outcomes of swallowing impairment score at 1 and 3 months after surgery (both P< 0.05). In addition, no significant changes in terms of jitter, shimmer, and maximum phonation time in both groups of patients at 1 and 3 months after surgery compared with their preoperative values (all P> 0.05). CONCLUSIONS: Voice and swallowing disorders may occur in some patients, either TOETVA or open thyroid surgery, which in most cases will recover within 3 months after surgery. The time to swallowing function recovery is relatively prolonged in patients following TOETVA, which may be probably associated with neck adhesion and fixation after the operation.