1
|
Curti N, Merli Y, Zengarini C, Starace M, Rapparini L, Marcelli E, Carlini G, Buschi D, Castellani GC, Piraccini BM, Bianchi T, Giampieri E. Automated Prediction of Photographic Wound Assessment Tool in Chronic Wound Images. J Med Syst 2024; 48:14. [PMID: 38227131 DOI: 10.1007/s10916-023-02029-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 12/22/2023] [Indexed: 01/17/2024]
Abstract
Many automated approaches have been proposed in literature to quantify clinically relevant wound features based on image processing analysis, aiming at removing human subjectivity and accelerate clinical practice. In this work we present a fully automated image processing pipeline leveraging deep learning and a large wound segmentation dataset to perform wound detection and following prediction of the Photographic Wound Assessment Tool (PWAT), automatizing the clinical judgement of the adequate wound healing. Starting from images acquired by smartphone cameras, a series of textural and morphological features are extracted from the wound areas, aiming to mimic the typical clinical considerations for wound assessment. The resulting extracted features can be easily interpreted by the clinician and allow a quantitative estimation of the PWAT scores. The features extracted from the region-of-interests detected by our pre-trained neural network model correctly predict the PWAT scale values with a Spearman's correlation coefficient of 0.85 on a set of unseen images. The obtained results agree with the current state-of-the-art and provide a benchmark for future artificial intelligence applications in this research field.
Collapse
Affiliation(s)
- Nico Curti
- Department of Physics and Astronomy, University of Bologna, 40127, Bologna, Italy
- Data Science and Bioinformatics Laboratory, IRCCS Institute of Neurological Sciences of Bologna, 40139, Bologna, Italy
| | - Yuri Merli
- Dermatology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Corrado Zengarini
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy.
| | - Michela Starace
- Dermatology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Luca Rapparini
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Emanuela Marcelli
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
- eDIMESLab, Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Gianluca Carlini
- Data Science and Bioinformatics Laboratory, IRCCS Institute of Neurological Sciences of Bologna, 40139, Bologna, Italy
| | - Daniele Buschi
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Gastone C Castellani
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | - Bianca Maria Piraccini
- Dermatology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138, Bologna, Italy
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| | | | - Enrico Giampieri
- Department of Medical and Surgical Sciences, University of Bologna, 40138, Bologna, Italy
| |
Collapse
|
2
|
Chen J, Liu Q, Wei Z, Luo X, Lai M, Chen H, Liu J, Xu Y, Li J. ETU-Net: efficient Transformer and convolutional U-style connected attention segmentation network applied to endoscopic image of epistaxis. Front Med (Lausanne) 2023; 10:1198054. [PMID: 37636575 PMCID: PMC10450218 DOI: 10.3389/fmed.2023.1198054] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Accepted: 07/19/2023] [Indexed: 08/29/2023] Open
Abstract
Epistaxis is a typical presentation in the otolaryngology and emergency department. When compressive therapy fails, directive nasal cautery is necessary, which strongly recommended operating under the nasal endoscope if it is possible. Limited by the operator's clinical experience, complications such as recurrence, nasal ulcer, and septum perforation may occur due to insufficient or excessive cautery. At present, deep learning technology is widely used in the medical field because of its accurate and efficient recognition ability, but it is still blank in the research of epistaxis. In this work, we first gathered and retrieved the Nasal Bleeding dataset, which was annotated and confirmed by many clinical specialists, filling a void in this sector. Second, we created ETU-Net, a deep learning model that smartly integrated the excellent performance of attention convolution with Transformer, overcoming the traditional model's difficulties in capturing contextual feature information and insufficient sequence modeling skills in picture segmentation. On the Nasal Bleeding dataset, our proposed model outperforms all others models that we tested. The segmentation recognition index, Intersection over Union, and F1-Score were 94.57 and 97.15%. Ultimately, we summarized effective ways of combining artificial intelligence with medical treatment and tested it on multiple general datasets to prove its feasibility. The results show that our method has good domain adaptability and has a cutting-edge reference for future medical technology development.
Collapse
Affiliation(s)
- Junyang Chen
- College of Information Engineering, Sichuan Agricultural University, Ya'an, China
| | - Qiurui Liu
- Department of Otorhinolaryngology Head and Neck Surgery, Ya'an People's Hospital, Ya'an, China
| | - Zedong Wei
- College of Information Engineering, Sichuan Agricultural University, Ya'an, China
| | - Xi Luo
- Department of Otorhinolaryngology Head and Neck Surgery, Ya'an People's Hospital, Ya'an, China
| | - Mengzhen Lai
- College of Information Engineering, Sichuan Agricultural University, Ya'an, China
| | - Hongkun Chen
- College of Information Engineering, Sichuan Agricultural University, Ya'an, China
| | - Junlin Liu
- College of Information Engineering, Sichuan Agricultural University, Ya'an, China
| | - Yanhong Xu
- Department of Otorhinolaryngology Head and Neck Surgery, Ya'an People's Hospital, Ya'an, China
| | - Jun Li
- Sichuan Key Laboratory of Agricultural Information Engineering, Ya'an, China
| |
Collapse
|
3
|
Horgos MS, Pop OL, Sandor M, Borza IL, Negrean R, Marc F, Major K, Sachelarie L, Grierosu C, Huniadi A. Laser in the Treatment of Atonic Wounds. Biomedicines 2023; 11:1815. [PMID: 37509454 PMCID: PMC10376327 DOI: 10.3390/biomedicines11071815] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Revised: 06/20/2023] [Accepted: 06/22/2023] [Indexed: 07/30/2023] Open
Abstract
Atonic wounds represent a major health problem, being frequently encountered in medical practice with consequences that have a negative impact on the patient's daily life as well as their general condition. In this study, a brand laser with a 12-watt probe was used to stimulate patients' wounds. We involved in this study a group of 65 patients, which was compared with a group of 30 patients, the latter not receiving this laser therapy. The data were accumulated from the questionnaire of subjective assessment of the laser impact on patients' condition as well as from the local evolution. We noticed the improvement of the local symptomatology which was found to be more effective in the patients from the study group compared to the reference group. The beneficial and positive effects, mainly on the symptoms but also on the local evolution of atonic wounds, can be observed in our study. We consider that this therapy is of major importance considering the lower costs both from the shortening of hospitalization and the long-term use of various substances. The early reintegration of patients into daily life is an important benefit for them.
Collapse
Affiliation(s)
- Maur Sebastian Horgos
- Department of Surgical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| | - Ovidiu Laurean Pop
- Department of Pathology, County Clinical Emergency Hospital, Faculty of Medicine and Pharmacy, University of Oradea, 1 December Sq. No. 10, 410087 Oradea, Romania
| | - Mircea Sandor
- Department of Surgical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| | - Ioan Lucian Borza
- Department of Morphological Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| | - Rodica Negrean
- Department of Preclinical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| | - Felicia Marc
- Department of Medical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| | - Klaudia Major
- Szabolcs-Szatmár-Bereg County Hospital and University Centre, Josa Andras, Szent István u. 68, 4400 Nyiregyhaza, Hungary
| | - Liliana Sachelarie
- Department of Preclinical Disciplines, Faculty of Dental Medicine, Apollonia University, 700511 Iasi, Romania
| | - Carmen Grierosu
- Department of Preclinical Disciplines, Faculty of Dental Medicine, Apollonia University, 700511 Iasi, Romania
| | - Anca Huniadi
- Department of Surgical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1st December Square 10, 410073 Oradea, Romania
| |
Collapse
|
4
|
Pagano C, Viseras Iborra CA, Perioli L. Recent Approaches for Wound Treatment. Int J Mol Sci 2023; 24:ijms24065959. [PMID: 36983030 PMCID: PMC10054067 DOI: 10.3390/ijms24065959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Accepted: 03/20/2023] [Indexed: 03/30/2023] Open
Abstract
Wounds are a serious global health problem [...].
Collapse
Affiliation(s)
- Cinzia Pagano
- Department of Pharmaceutical Sciences, University of Perugia, 06123 Perugia, Italy
| | - César Antonio Viseras Iborra
- Department of Pharmacy and Pharmaceutical Technology, Faculty of Pharmacy, University of Granada, 18071 Granada, Spain
| | - Luana Perioli
- Department of Pharmaceutical Sciences, University of Perugia, 06123 Perugia, Italy
| |
Collapse
|
5
|
Automated Wound Image Segmentation: Transfer Learning from Human to Pet via Active Semi-Supervised Learning. Animals (Basel) 2023; 13:ani13060956. [PMID: 36978498 PMCID: PMC10044392 DOI: 10.3390/ani13060956] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 02/24/2023] [Accepted: 03/06/2023] [Indexed: 03/09/2023] Open
Abstract
Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications regarding wound management for pets. Precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for chronic wounds. In this work, we introduced a novel pipeline for the segmentation of pet wound images. Starting from a model pre-trained on human-based wound images, we applied a combination of transfer learning (TL) and active semi-supervised learning (ASSL) to automatically label a large dataset. Additionally, we provided a guideline for future applications of TL+ASSL training strategy on image datasets. We compared the effectiveness of the proposed training strategy, monitoring the performance of an EfficientNet-b3 U-Net model against the lighter solution provided by a MobileNet-v2 U-Net model. We obtained 80% of correctly segmented images after five rounds of ASSL training. The EfficientNet-b3 U-Net model significantly outperformed the MobileNet-v2 one. We proved that the number of available samples is a key factor for the correct usage of ASSL training. The proposed approach is a viable solution to reduce the time required for the generation of a segmentation dataset.
Collapse
|