biomedical engineering-related Feed back for editing: Reviewer #1: Overall, the

biomedical engineering-related
Feed back for editing:
Reviewer #1: Overall, the manuscript is well organized.
1-The abstract needs to be re-written properly.
2-The limitation of the reviewed works need to be highlighted.
3-Authors should add a paragraph to explain CAD system in general. I recommend the following works to be included and discussed in which they are explained the CAD system and also explained (thresholding and clustering) based segmentation.
Title:(An efficient CAD system for ALL cell identification from microscopic blood images). Link:(https://link.springer.com/article/10.1007/s11042-020-10066-6).
Title:(Efficient computer-aided diagnosis technique for leukaemia cancer detection). Link:(https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/iet-ipr.2020.0978).
4- Some typos and language mistakes are available. They need to be corrected.
Reviewer #3: No Comments
Reviewer #4: Alzheimer’s disease is one of the most devastating diseases in people over 65 and, therefore, an early accurate detection is paramount.
This is a fairly well-written and well-structured paper, in which the authors present a survey of existing AD detection techniques divided into three categories: signal processing, image processing, and machine learning techniques. They firstly discuss biomarkers and their classification, and then, the detection techniques based on those categories are described and briefly compared. Authors also provide a discussion on some challenges and recommended directions for AD detection research.
My main concern about this paper is whether it is appropriate for MTAP journal. The authors list and classify many works, but they are superficially described and very succinctly compared, without detail. I do not see a strong contribution that motivates me to recommend it for publication in this journal.
Some other comments:
Many acronyms are used throughout the paper but in an inconsistent way. They should be defined at first mention and used consistently thereafter (.eg., MRI, CT, CSF, EEG, QEEG, GM, WM, SVM, AUC, etc.). For example, some of them (MRI, CSF, EEG, etc.) are defined when they have previously been used several times in the text. Moreover, MRI is defined three times (also in table 1). PET is defined four times. Once AD is defined the first time, use it instead of ‘Alzheimer’s Disease’ in all the paper.
Table 1 is neither discussed nor mentioned in the text. In it there are some references (e.g., 21 to 23) that have not been included in the previous works discussion in Section 1. Imho, authors should also include there a description/discussion of them, although works [22] and [23] are mentioned later.
Section 4 is too concise and schematic, Table II should be explained in detail.
Please, explain what T1 and T2 represent (and their units) in section 3.2.4.
Some typos or possible mistakes to be corrected:
– review ¿by? [8, 9], review ¿by? [10], and so on -> I suggest the use of ‘in’ preposition.
– we classify biomarkers into six categories: biochemical, neurogenetic, neurophysiological, neuropsychological, and digital biomarkers -> we classify biomarkers into six categories: biochemical, neurogenetic, neurophysiological, NEUROIMAGING, neuropsychological, and digital biomarkers
– divided them into two different categories, namely basic, specific, and novel. The basic biochemical biomarkers are efficient in ruling out critical differentiate of diagnosis of AD; however, specific biochemical biomarkers impact the central molecular pathogenesis of this disease [23] -> into two or three categories? three are mentioned (basic, specific and novel) but only two are described (basic and specific).
– both terms are used: QEEG and qEEG
– Détection -> Detection
– 3.22 Brain Tissue Segmentation -> 3.2.2. Brain Tissue Segmentation
– Remove one ‘,’ in line 17 of page 10 (features, , can improve diagnosis)
– Revise this sentence: Another study mainly concentrated on the Bayesian network, which is defined as a probabilistic graphical model representing the variables and their dependencies using a directed acyclic graph [123].